Understanding Data Analysis in Nursing Research
Data analysis in nursing research involves rendering individual data points into meaningful information, leading to knowledge generation. The process includes qualitative and quantitative analysis to organize and interpret data effectively. Techniques such as data reduction, data display, and conclusion drawing are essential for deriving valuable insights. Understanding the different levels of data and selecting appropriate descriptive and inferential statistics is crucial for effective analysis.
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. Download presentation by click this link. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
E N D
Presentation Transcript
Unit Unit XI: Data Analysis in XI: Data Analysis in nursing research research nursing Prepared by: NUR 500 Research team 1STsemester 38/39. H
OBJECTIVES OBJECTIVES By the completion of this module, the participant will be able to: Define data analysis Determine the different levels of data Describe a method for determining the appropriate descriptive and inferential statistic
Data Analysis Data Analysis Data Analysis is: A methodology by which individual data points are rendered into meaningful and intelligible information A product of data analysis in research is knowledge Polit & Beck 2017
Categories Categories of of Data Analysis Data Analysis Qualitative Analysis: The systematic, rational process by which narrative (written data) are organized into meaningful descriptions, of themes, patterns, models or theories Quantitative Analysis: Uses statistical procedures to reduce, summarize, organize, evaluate, interpret, and communicate numeric information Polit & Beck 2017
Qualitative Analysis Qualitative Analysis Techniques will be different depending on the qualitative design- see Module 8 for Qualitative Designs All methods include: Data Reduction Data Display Conclusion drawing/ Verification Polit & Beck 2017
Qualitative: Data Reduction Qualitative: Data Reduction The process of selecting, focusing, simplifying, abstracting and transforming the raw data (written narratives) into categories or themes Polit & Beck 2017
Qualitative: Data Display Qualitative: Data Display Organized assembly of the information using such forms such as tables or matching Polit & Beck 2017
Qualitative: Conclusion Qualitative: Conclusion Qualitative: Conclusion Qualitative: Conclusion Drawing/ Verification Drawing/ Verification Involves attaching meaning to the findings This could be a linear findings or may occur together Polit & Beck 2017
Quantitative Analysis Quantitative Analysis Techniques will be different depending on the quantitative design- see Module 9 and 10 for Quantitative Designs Quantitative falls into two statistical categories: Descriptive Statistics Use to describe and synthesis data Inferential Statistics The use of a statistic created from a smaller group (sample) to draw a conclusion about a population Polit & Beck 2017
Choosing a Statistical Test Choosing a Statistical Test An appropriate statistical procedure is a function of: The research design The level of data provided by the data collection instrument. Polit & Beck 2017
The Research Design The Research Design Descriptive Statistics Exploratory Descriptive Designs (case studies) Correlational Designs Inferential Statistics Correlational Designs Comparative Designs Experimental and Quasi-Experimental Designs Polit & Beck 2017
Levels of Data Levels of Data Nominal Measurement Ordinal Measurement Interval Measurement Ratio Measurement Responses of an instrument determine your level of data Polit & Beck 2017
Nominal Nominal Measurement Measurement The assignment of numbers to simply classify characteristics into categories Sometimes called dummy variables (Used to quantify variables) No= 0 Yes= 1 Female= 1 Male= 0 Polit & Beck 2017
Ordinal Ordinal Measurement Measurement Permits the sorting of objects on the basis of their standing on an attribute relative to each other A higher score is better (or worse), but how much better (or worse) is not known Polit & Beck 2017
Interval Measurement Interval Measurement Determines both the rank ordering of objects on an attribute and the distance between those objects Example: Scores on an intelligence test Temperature Polit & Beck 2017
Ratio Measurement Ratio Measurement Determines the rank ordering of objects on the attribute and the absolute magnitude of the attribute for the object as there is a rational, absolute zero Examples: Weight (0,1,2 lbs) Length confidently say that an object is twice as long as another object Polit & Beck 2017
Robustness of Test Robustness of Test Ability of the test to analyze data that is critically accepted than other tests Assumptions are violated when you run tests on data that is not appropriate Non Parametric vs. Parametric Statistics Polit & Beck 2017
Non Non- - Parametric Parametric Not as robust as parametric Assumptions: Observations are independent each member of the sample is their own Ordinal or Nominal data Polit & Beck 2017
Parametric Parametric Most powerful/ robust of statistical test Assumptions: Observations are independent Data are normally distributed Populations are homogeneous- are in all other ways alike Interval or Ratio data Polit & Beck 2017
Statistical Choices Matrix Statistical Choices Matrix
Case Studies, Exploratory Case Studies, Exploratory Descriptive Design Descriptive Design Case Studies, Exploratory Descriptive Designs Example Nominal or Categorical Data Counts Frequencies Percentiles 25 female, 45 male Ordinal Data Measures of Central Tendency Mean Median Mode 50% above / 50% below Most frequent Interval or Ratio Data Measures of Variation Range Standard Deviation Standard Error of the Mean Majority of the population fell around the mean
Correlational Designs Correlational Designs Correlational Designs Nominal or Categorical Data Tetrachloric phi Biserial Spearman s rho Kentall s Tau Ordinal Data Interval or Ratio Data Pearson s Moment Correlation (r) Coefficient of Determination(r2) All of these are correlational techniques, and come to a single number that can give you the strength of the relationship
Comparative Designs Comparative Designs Comparative Designs Nominal or Categorical Data Chi-Square Ordinal Data Two Groups: Mann-Whitney U Wilcoxin Rank Three or More Groups: Kruskall-Wallis Two Groups: t-test Three or More Groups: Analysis of Variance (ANOVA) Interval or Ratio Data Polit & Beck 2017
Experimental and Experimental and Quasi Quasi- - Experimental Designs Experimental Designs Experimental and Quasi- Experimental Designs Nominal or Categorical Data Chi-Square Ordinal Data Two Groups: Mann-Whitney U Wilcoxin Rank Three or More Groups: Kruskall-Wallis Two Groups: t-test Three or More Groups: Analysis of Variance (ANOVA) Interval or Ratio Data Polit & Beck 2017
Conclusion Conclusion Data analysis may be quantitative or qualitative Quantitative analysis uses statistical procedures Descriptive Inferential Choice of test is a function of: The research design The level of data provided by your data collection procedures
Thank you Thank you
